Many-MobileNet: Multi-Model Augmentation for Robust Retinal Disease Classification

TL;DR

Many-MobileNet introduces a multi-model fusion approach using lightweight CNNs with diverse data augmentations to improve retinal disease classification robustness in data-scarce scenarios.

Contribution

It presents a novel multi-model fusion strategy that enhances generalization and robustness in retinal disease classification with lightweight CNNs.

Findings

Improved classification accuracy on retinal disease datasets.

Enhanced robustness against overfitting in limited data scenarios.

Maintained computational efficiency with lightweight models.

Abstract

In this work, we propose Many-MobileNet, an efficient model fusion strategy for retinal disease classification using lightweight CNN architecture. Our method addresses key challenges such as overfitting and limited dataset variability by training multiple models with distinct data augmentation strategies and different model complexities. Through this fusion technique, we achieved robust generalization in data-scarce domains while balancing computational efficiency with feature extraction capabilities.